Determining a match between the subjects of first and second images as a function of decimal-number representations of regions of the first and second images. The decimal-number representations are generated by performing discrete transforms on the regions so as to obtain discrete-transform coefficients, performing local-bit-pattern encoding of the coefficients to create data streams, and converting the data streams to decimal numbers. In one embodiment, the first and second images depict periocular facial regions, and the disclosed techniques can be used for face recognition, even where a small portion of a person's face is captured in an image. Subspace modeling may be used to improve accuracy.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method of matching first features of first image data with second features of second image data, comprising: receiving, by a feature-matching system, the first image data; applying, by the feature-matching system, a discrete transform to a region of the first image data containing the first features so as to generate a first set of transform coefficients; executing, by the feature-matching system, a local binary pattern (LBP) encoding algorithm to encode the first set of transform coefficients into a set of first encoded data streams; converting, by the feature-matching system, each of the first encoded data streams into a decimal number so as to create a first decimal-number representation of the region of the first image data; and executing, by the feature-matching system, a matching algorithm for determining a match as a function of the first decimal number representation and a second decimal representation of a region of the second image data containing the second features.
2. A method according to claim 1 , further comprising: receiving, by the feature-matching system, the second image data; applying, by the feature-matching system, the discrete transform to the region of the second image data containing the second features so as to generate a second set of transform coefficients; executing, by the feature-matching system, the LBP encoding algorithm to encode the second set of transform coefficients into a set of second encoded data streams; and converting, by the feature-matching system, each of the second encoded data streams into a decimal number so as to create the second decimal-number representation of the second image data.
3. A method according to claim 1 , wherein said executing an LBP encoding algorithm includes executing an LBP algorithm using ordering determined as a function of a fitness function derived by permutating generations of possible ordering schemes.
4. A method according to claim 3 , wherein said executing an LBP encoding algorithm includes executing an LBP encoding algorithm implementing a non-central thresholding center.
5. A method according to claim 3 , wherein said executing an LBP encoding algorithm includes executing an LBP algorithm that selects active neighbors according to a selection scheme that considers angle and/or radius.
6. A method according to claim 3 , wherein said executing an LBP encoding algorithm includes executing an LBP algorithm using, for decimal conversion, a base other than base 2.
7. A method according to claim 6 , wherein said using a base other than base 2 includes using a fractional base.
8. A method according to claim 1 , wherein said applying a discrete transform includes applying a Walsh-Hadamard transform.
9. A method according to claim 1 , wherein said applying a discrete transform includes applying a discrete cosine transform.
10. A method according to claim 1 , wherein said applying a discrete transform includes applying a discrete Fourier transform.
11. A method according to claim 1 , wherein said applying a discrete transform includes applying a discrete Hartley transform.
12. A non-transitory machine-readable storage medium containing machine-executable instructions for performing a method of matching first features of first image data with second features of second image data, said machine-executable instructions comprising: a first set of machine-executable instructions for receiving the first image data; a second set of machine-executable instructions for applying a discrete transform to a region of the first image data containing the first features so as to generate a first set of transform coefficients; a third set of machine-executable instructions for executing a local binary pattern (LBP) encoding algorithm to encode the first set of transform coefficients into a set of first encoded data streams; a fourth set of machine-executable instructions for converting each of the first encoded data streams into a decimal number so as to create a first decimal-number representation of the region of the first image data; and a fifth set of machine-executable instructions for executing a matching algorithm for determining a match as a function of the first decimal number representation and a second decimal representation of a region of the second image data containing the second features.
13. A non-transitory machine-readable storage medium according to claim 12 , further comprising: a sixth set of machine-executable instructions for receiving the second image data; a seventh set of machine-executable instructions for applying the discrete transform to the region of the second image data containing the second features so as to generate a second set of transform coefficients; an eighth set of machine-executable instructions for executing the LBP encoding algorithm to encode the second set of transform coefficients into a set of second encoded data streams; and a ninth set of machine-executable instructions for converting each of the second encoded data streams into a decimal number so as to create the second decimal-number representation of the second image data.
14. A non-transitory machine-readable storage medium according to claim 12 , wherein said third set of machine-executable instructions includes machine-executable instructions for executing an LPB algorithm using ordering determined as a function of a fitness function derived by permutating generations of possible ordering schemes.
15. A non-transitory machine-readable storage medium according to claim 14 , wherein said third set of machine-executable instructions includes machine-executable instructions for executing an LBP encoding algorithm implementing a non-central thresholding center.
16. A non-transitory machine-readable storage medium according to claim 14 , wherein said third set of machine-executable instructions includes machine-executable instructions for executing an LBP algorithm that selects active neighbors according to a selection scheme that considers angle and/or radius.
17. A non-transitory machine-readable storage medium according to claim 14 , wherein said third set of machine-executable instructions includes machine-executable instructions for executing an LBP algorithm using, for decimal conversion, a base other than base 2.
18. A non-transitory machine-readable storage medium according to claim 17 , wherein said third set of machine-executable instructions includes machine-executable instructions for executing an LBP algorithm using a fractional base.
19. A non-transitory machine-readable storage medium according to claim 12 , wherein said second set of machine-executable instructions includes machine-executable instructions for applying a Walsh-Hadamard transform.
20. A non-transitory machine-readable storage medium according to claim 12 , wherein said second set of machine-executable instructions includes machine-executable instructions for applying a discrete cosine transform.
21. A non-transitory machine-readable storage medium according to claim 12 , wherein said second set of machine-executable instructions includes machine-executable instructions for applying a discrete Fourier transform.
22. A non-transitory machine-readable storage medium according to claim 12 , wherein said second set of machine-executable instructions includes machine-executable instructions for applying a discrete Hartley transform.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
September 26, 2013
October 27, 2015
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.